3D point cloud semantic segmentation: state of the art and challenges

• Published in: 工程科学学报 Vol. 45; no. 10; pp. 1653 - 1665
• Main Authors: Yixian WANG, Yufan HU, Qingqun KONG, Hui ZENG, Lixin ZHANG, Bin FAN
• Format: Journal Article
• Language: Chinese
• Published: Science Press 01.10.2023
• Subjects: 3d vision; deep learning; network framework; point cloud; semantic segmentation
• ISSN: 2095-9389
• DOI: 10.13374/j.issn2095-9389.2022.12.17.004

Decrease in the cost of acquiring 3D point cloud data coupled with the rapid advancements in GPU computing power have resulted in an increased demand for 3D point cloud semantic segmentation in numerous 3D visual applications, including but not limited to autonomous driving, industrial control, and MR/XR, which further advances the development of deep learning methods in 3D point cloud semantic segmentation. Recently, many novel deep learning network architectures, such as RandLA-Net and Point Transformer, have been proposed and have achieved notable improvements in semantic segmentation accuracy while decreasing the computational load. However, previous research on 3D point cloud semantic segmentation methods has focused primarily on relatively early works, whose approaches have been gradually abandoned over the years and cannot accurately reflect the current research status. Moreover, the existing methods have been categorized based on their input data types, making it difficult to compare the segmentation